Connect with us

Hi, what are you looking for?

Photo by Markus Spiske on Unsplash


Cybersecurity Defenders Are Expanding Their AI Toolbox

Deep reinforcement learning for cybersecurity could help deter adversaries. close In simulations against three distinct types of adversaries, deep reinforcement learning demonstrated the promise of autonomous AI in proactive cyber defense.

Scientists have taken a key step toward harnessing a form of artificial intelligence known as deep reinforcement learning, or DRL, to protect computer networks.

When faced with sophisticated cyberattacks in a rigorous simulation setting, deep reinforcement learning was effective at stopping adversaries from reaching their goals up to 95% of the time. The outcome offers promise for a role for autonomous AI in proactive cyber defense.

Scientists from the Department of Energy’s Pacific Northwest National Laboratory documented their findings in a research paper and presented their work Feb. 14 at a workshop on AI for Cybersecurity during the annual meeting of the Association for the Advancement of Artificial Intelligence in Washington, D.C.

The starting point was the development of a simulation environment to test multistage attack scenarios involving distinct types of adversaries. Creation of such a dynamic attack-defense simulation environment for experimentation itself is a win. The environment offers researchers a way to compare the effectiveness of different AI-based defensive methods under controlled test settings.

Such tools are essential for evaluating the performance of deep reinforcement learning algorithms. The method is emerging as a powerful decision-support tool for cybersecurity experts — a defense agent with the ability to learn, adapt to quickly changing circumstances, and make decisions autonomously. While other forms of artificial intelligence are standard to detect intrusions or filter spam messages, deep reinforcement learning expands defenders’ abilities to orchestrate sequential decision-making plans in their daily face-off with adversaries.

Deep reinforcement learning offers smarter cybersecurity, the ability to detect changes in the cyber landscape earlier, and the opportunity to take preemptive steps to scuttle a cyberattack.

DRL: Decisions in a Broad Attack Space

“An effective AI agent for cybersecurity needs to sense, perceive, act and adapt, based on the information it can gather and on the results of decisions that it enacts,” said Samrat Chatterjee, a data scientist who presented the team’s work. “Deep reinforcement learning holds great potential in this space, where the number of system states and action choices can be large.”

DRL, which combines reinforcement learning and deep learning, is especially adept in situations where a series of decisions in a complex environment need to be made. Good decisions leading to desirable results are reinforced with a positive reward (expressed as a numeric value); bad choices leading to undesirable outcomes are discouraged via a negative cost.

It’s similar to how people learn many tasks. A child who does their chores might receive positive reinforcement with a desired playdate; a child who doesn’t do their work gets negative reinforcement, like the takeaway of a digital device.

“It’s the same concept in reinforcement learning,” Chatterjee said. “The agent can choose from a set of actions. With each action comes feedback, good or bad, that becomes part of its memory. There’s an interplay between exploring new opportunities and exploiting past experiences. The goal is to create an agent that learns to make good decisions.”


The team used an open-source software toolkit known as Open AI Gym as a basis to create a custom and controlled simulation environment to evaluate the strengths and weaknesses of four deep reinforcement learning algorithms.

The team used the MITRE ATT&CK framework, developed by MITRE Corp., and incorporated seven tactics and 15 techniques deployed by three distinct adversaries. Defenders were equipped with 23 mitigation actions to try to halt or prevent the progression of an attack.

Stages of the attack included tactics of reconnaissance, execution, persistence, defense evasion, command and control, collection and exfiltration (when data is transferred out of the system). An attack was recorded as a win for the adversary if they successfully reached the final exfiltration stage.

“Our algorithms operate in a competitive environment — a contest with an adversary intent on breaching the system,” said Chatterjee. “It’s a multistage attack, where the adversary can pursue multiple attack paths that can change over time as they try to go from reconnaissance to exploitation. Our challenge is to show how defenses based on deep reinforcement learning can stop such an attack.”

Rewards and penalties help train children and deep reinforcement learning algorithms alike.

Like a toddler starting to walk learns from bumps and bruises, algorithms based on deep reinforcement learning, or DRL, are trained through rewards for good decisions and penalties for bad decisions. DQN outpaces other approaches

The team trained defensive agents based on four deep reinforcement learning algorithms: DQN (Deep Q-Network) and three variations of what’s known as the actor-critic approach. The agents were trained with simulated data about cyberattacks, then tested against attacks that they had not observed in training.

DQN performed the best.

Least sophisticated attacks (based on varying levels of adversary skill and persistence): DQN stopped 79% of attacks midway through attack stages and 93% by the final stage.

Moderately sophisticated attacks: DQN stopped 82% of attacks midway and 95% by the final stage.

Most sophisticated attacks: DQN stopped 57% of attacks midway and 84% by the final stage — far higher than the other three algorithms.

“Our goal is to create an autonomous defense agent that can learn the most likely next step of an adversary, plan for it, and then respond in the best way to protect the system,” Chatterjee said.

Despite the progress, no one is ready to entrust cyber defense entirely up to an AI system. Instead, a DRL-based cybersecurity system would need to work in concert with humans, said coauthor Arnab Bhattacharya, formerly of PNNL.

“AI can be good at defending against a specific strategy but isn’t as good at understanding all the approaches an adversary might take,” Bhattacharya said. “We are nowhere near the stage where AI can replace human cyber analysts. Human feedback and guidance are important.”

In addition to Chatterjee and Bhattacharya, authors of the AAAI workshop paper include Mahantesh Halappanavar of PNNL and Ashutosh Dutta, a former PNNL scientist. The work was funded by DOE’s Office of Science. Some of the early work that spurred this specific research was funded by PNNL’s Mathematics for Artificial Reasoning in Science initiative through the Laboratory Directed Research and Development program.

Courtesy of Pacific Northwest National Laboratory 

Photo by Markus Spiske on Unsplash

Sign up for daily news updates from CleanTechnica on email. Or follow us on Google News!

Have a tip for CleanTechnica, want to advertise, or want to suggest a guest for our CleanTech Talk podcast? Contact us here.

Electrifying Industrial Heat for Steel, Cement, & More

I don't like paywalls. You don't like paywalls. Who likes paywalls? Here at CleanTechnica, we implemented a limited paywall for a while, but it always felt wrong — and it was always tough to decide what we should put behind there. In theory, your most exclusive and best content goes behind a paywall. But then fewer people read it! We just don't like paywalls, and so we've decided to ditch ours. Unfortunately, the media business is still a tough, cut-throat business with tiny margins. It's a never-ending Olympic challenge to stay above water or even perhaps — gasp — grow. So ...
If you like what we do and want to support us, please chip in a bit monthly via PayPal or Patreon to help our team do what we do! Thank you!

The mission of the U.S. Energy Department is to ensure America’s security and prosperity by addressing its energy, environmental and nuclear challenges through transformative science and technology solutions. Learn more.


You May Also Like

Autonomous Vehicles

The danger of artificial intelligence is a common theme in science fiction because it allows authors and filmmakers to explore ethical and societal questions...

Autonomous Vehicles

One of Tesla’s main contributions to the world, besides popularizing the electric vehicle, includes its huge leaps and bounds in the artificial intelligence sector....

Green Economy

This is the second part of a two-part story. You can find Part 1 here. What I’m Probably Worth Listening To About I think...

Climate Change

Up until now, manual mapping of wetlands was the only real choice, and it was time consuming due to data processing, curation, and manual...

Copyright © 2023 CleanTechnica. The content produced by this site is for entertainment purposes only. Opinions and comments published on this site may not be sanctioned by and do not necessarily represent the views of CleanTechnica, its owners, sponsors, affiliates, or subsidiaries.